The DOI matches its Crossref record, with a small difference in title or year; 31 of the 31 references it cites were found in a registry or an index; 2 of the 14 sources its claims cite were checked for support.
ImageNet classification with deep convolutional neural networks
Open accessAbstract
We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0%, respectively, which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overfitting in the fully connected layers we employed a recently developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
42 Own result · 21 Own interpretation · 7 No basis given · 4 No full text of the sources · 3 Sources not found · 2 Supported · 2 Not checked yet · 1 Own method
Every source the paper cites for this claim was checked and supports it.
In the paper
“This technique reduces complex co adaptations of neurons, since a neuron cannot rely on the presence of particular other neurons.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.2. Dropout
What the sources say
- Supportedcites [12] 12. Hinton, G., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012). source
The paper states on p. 1 that dropout prevents complex co-adaptations by randomly omitting hidden units, so a hidden unit cannot rely on other hidden units being present. This directly supports the citing sentence. (LLM, conf=0.95)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“There is, however, a very efficient version of model combination that only costs about a factor of two during training.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.2. Dropout
What the sources say
- Supportedcites [12] 12. Hinton, G., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012). source
The paper describes dropout as an efficient way to combine many neural-network models (p. 1). In F.6 Training (p. 17), it reports that ImageNet training took roughly four days with dropout versus two days without it, supporting the approximate factor-of-two training cost. (LLM, conf=0.88)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This scheme reduces our top-1 and top-5 error rates by 1.7% and 1.2%, respectively, as compared with a net with half as many kernels in each convolutional layer trained on one GPU.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.2. Training on multiple GPUs
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The size of our network made overfitting a significant problem, even with 1.2 million labeled training examples”
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“So these data augmentation schemes are, in effect, computationally free.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.1. Data augmentation
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- It may state two separate claims as one. 18
- Probably not a substantial claim. 26
- The quote only partly states this claim. 2
Create a free account to see these claims.
Create a free account to see these assumptions.
34 more claims
Create a free account to see all 82 claims and to verify the 3 references still open.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In the field of DL, the CNN is the most famous and commonly employed algorithm [30, 71–75].”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [30]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Convolutional neural networks (CNNs), built for spatial data, have demonstrated performance comparable to that of specialists in cancer detection and tumor segmentation [15,16,17,18,19,20].”
From Artificial Intelligence in Clinical Oncology: From Productivity Enhancement to Creative Discovery (2025) · cites this paper as [16]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Deep CNN architectures with 8, even 22 layers [4], [33], can be useful even for CADe problems where the available training datasets are limited.”
From Deep convolutional neural networks for computer-aided detection: cnn architectures, dataset characteristics and transfer learning (2016) · cites this paper as [4]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Fully convolutional neural networks (fCNNs) have provided state-of-the-art performance for object classification and image segmentation (1).”
From Fully automated, real-time 3D ultrasound segmentation to estimate first trimester placental volume using deep learning (2018) · cites this paper as [1]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The first wave saw the emergence of deep learning as the dominant paradigm for analyzing high-dimensional biological data.”
From The next paradigm in bioinformatics: a review of multi-agent systems and foundational models for end-to-end scientific discovery (2026) · cites this paper as [1]
Experimental — accuracy not yet measured
19 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
“we found that removing any convolutional layer (each of which contains no more than 1% of the model's parameters) resulted in inferior performance.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.5. Overall architecture
“The third convolutional layer has 384 kernels of size 3 × 3 × 256”
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,884
Self-citationLearning Internal Representations by Error Propagation
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1985) · doi:10.21236/ada164453 · Cited by 16,501
Self-citation(2010) · International Conference on Machine Learning · Cited by 13,995
Self-citationImproving neural networks by preventing co-adaptation of feature detectors
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012) · arXiv · doi:10.48550/arxiv.1207.0580 · Cited by 6,382
Self-citationFukushima, K. (1980) · Biological Cybernetics · doi:10.1007/bf00344251 · Cited by 5,759
LabelMe: A Database and Web-Based Tool for Image Annotation
Russell, B. C., Torralba, A., Murphy, K. P., & Freeman, W. T. (2008) · International Journal of Computer Vision · doi:10.1007/s11263-007-0090-8 · Cited by 4,210
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
Research works printed but not linked: 13
- Berg A., 2010, Large scale visual recognition challenge
- Deng J., 2009, CVPR09
- Krizhevsky A., 2009, Department of Computer Science
- Krizhevsky A., 2010, Convolutional deep belief networks on cifar-10. Unpublished manuscript
- Krizhevsky A., 2011, ESANN
- LeCun Y., 1990, Advances in Neural Information Processing Systems
- LeCun Y., 1985, Une procedure d'apprentissage pour reseau a seuil asymmetrique (a learning scheme for asymmetric threshold networks)
- 10.5555/1896300.1896315 · DOI
- Mensink T., 2012, Italy
- 10.5555/3104322.3104425 · DOI
- Rumelhart D.E., 1985, DTIC Document
- 10.5555/938980.939477 · DOI
- Werbos P., 1974, Beyond regression: New tools for prediction and analysis in the behavioral sciences
Cited by
Items 58,001–58,100 of 108,438
Cho, W. I., Lee, H. S., Yoon, J. W., Kim, S., & Kim, N. S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.04231 · Cited by 9
Exploiting Kernel Sparsity and Entropy for Interpretable CNN CompressionPreprint
Li, Y., Lin, S., Zhang, B., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.04368 · Cited by 8
Face Completion with Semantic Knowledge and Collaborative Adversarial LearningPreprint
Liao, H., Funka-Lea, G., Zheng, Y., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.03252 · Cited by 8
A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban ScenesPreprint
Zhang, Y., David, P., Foroosh, H., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.09953 · Cited by 8
Tango: A Deep Neural Network Benchmark Suite for Various AcceleratorsPreprint
Karki, A., Keshava, C. P., Shivakumar, S. M., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.04987 · Cited by 8
CodeX: Bit-Flexible Encoding for Streaming-based FPGA Acceleration of DNNsPreprint
Samragh, M., Javaheripi, M., & Koushanfar, F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.05582 · Cited by 12
Lyu, J., Zhang, S., Qi, Y., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.08624 · Cited by 8
Incremental Learning with Maximum Entropy Regularization: Rethinking Forgetting and IntransigencePreprint
Kim, D., Bae, J.-H., Jo, Y., & Choi, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.00829 · Cited by 23
Yamaguchi, M., Iwamoto, G., Tamukoh, H., & Morie, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.07707 · Cited by 10
Ayrey, E., Hayes, D. J., Kilbride, J. B., Fraver, S., Kershaw, J. A., Cook, B. D., & Weiskittel, A. R. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/580514 · Cited by 8
Attribution-driven Causal Analysis for Detection of Adversarial ExamplesPreprint
Jha, S., Raj, S., Fernandes, S. L., Jha, S. K., Jha, S., Verma, G., Jalaian, B. A., & Swami, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.05821 · Cited by 16
Accelerating Deep Unsupervised Domain Adaptation with Transfer Channel PruningPreprint
Yu, C., Wang, J., Chen, Y., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.02654 · Cited by 8
BridgeNet: A Continuity-Aware Probabilistic Network for Age EstimationPreprint
Li, W., Lu, J., Feng, J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.03358 · Cited by 8
Deep Learning Based Computed Tomography Whys and WhereforesPreprint
Bazrafkan, S., Nieuwenhove, V. V., Soons, J. A. M., Beenhouwer, J. D., & Sijbers, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.03908 · Cited by 10
Finding and Visualizing Weaknesses of Deep Reinforcement Learning AgentsPreprint
Rupprecht, C., Ibrahim, C., & Pal, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.01318 · Cited by 29
PaintBot: A Reinforcement Learning Approach for Natural Media PaintingPreprint
Jia, B., Chen, F., Brandt, J., Kim, B., & Manocha, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.02201 · Cited by 12
On Arrhythmia Detection by Deep Learning and Multidimensional RepresentationPreprint
Rajput, K. S., Wibowo, S., Hao, C., & Majmudar, M. D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.00138 · Cited by 11
Do, T.-T., Tran, T. B., Reid, I. D., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.08720 · Cited by 8
Learning from Multi-domain Artistic Images for Arbitrary Style TransferPreprint
Xu, Z., Wilber, M. J., Chen, F., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.09987 · Cited by 8
Multi-Target Embodied Question AnsweringPreprint
Yu, L., Chen, X., Gkioxari, G., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.04686 · Cited by 8
SWNet: Small-World Neural Networks and Rapid ConvergencePreprint
Javaheripi, M., Rouhani, B. D., & Koushanfar, F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.04862 · Cited by 12
Surface Defect Classification in Real-Time Using Convolutional Neural NetworksPreprint
Arikan, S., Varanasi, K., & Stricker, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.04671 · Cited by 21
MinCall - MinION end2end convolutional deep learning basecallerPreprint
Miculinić, N., Ratković, M., & Šikić, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.10337 · Cited by 8
Human Activity Recognition Based on Transfer Learning
Pang, J. (2018) · Digital Commons - University of South Florida (University of South Florida) · Cited by 7
Known-class Aware Self-ensemble for Open Set Domain AdaptationPreprint
Lian, Q., Li, W., Chen, L., & Duan, L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.01068 · Cited by 9
SpecNet: Spectral Domain Convolutional Neural NetworkPreprint
Guan, B., Zhang, J., Sethares, W. A., Kijowski, R., & Liu, F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.10915 · Cited by 9
Incremental Learning Using a Grow-and-Prune Paradigm with Efficient Neural NetworksPreprint
Dai, X., Yin, H., & Jha, N. K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.10952 · Cited by 8
Namazi, B., Sankaranarayanan, G., & Devarajan, V. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.08983 · Cited by 10
Inferring the landscape of recombination using recurrent neural networksPreprint
Adrion, J. R., Galloway, J., & Kern, A. D. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/662247 · Cited by 8
Learning Context Graph for Person SearchPreprint
Yan, Y., Zhang, Q., Ni, B., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.01830 · Cited by 8
Image Matters: Visually modeling user behaviors using Advanced Model ServerPreprint
Ge, T., Zhao, L., Zhou, G., Chen, K., Liu, S., Yi, H., Hu, Z., Liu, B., Sun, P., Liu, H., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.06505 · Cited by 13
Layered SGD: A Decentralized and Synchronous SGD Algorithm for Scalable Deep Neural Network TrainingPreprint
Yu, K., Flynn, T., Yoo, S., & D’Imperio, N. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.05936 · Cited by 8
An IoT Based Framework For Activity Recognition Using Deep Learning TechniquePreprint
d'Sa, A. G., & Prasad, B. G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.07247 · Cited by 8
TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports ApplicationsPreprint
Huang, Y.-C., Liao, I.-N., Chen, C., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.03698 · Cited by 8
Attending to Discriminative Certainty for Domain AdaptationPreprint
Kurmi, V. K., Kumar, S., & Namboodiri, V. P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.03502 · Cited by 6
Regularizing by the Variance of the Activations' Sample-VariancesPreprint
Littwin, E., & Wolf, L. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.08764 · Cited by 10
Rank selection of CP-decomposed convolutional layers with variational Bayesian matrix factorization
Astrid, M., Lee, S., & Seo, B.-S. (2018) · International Conference on Advanced Communication Technology · doi:10.23919/icact.2018.8323749 · Cited by 8
Energy-Efficient Processing and Robust Wireless Cooperative Transmission for Edge InferencePreprint
Yang, K., Shi, Y., Yu, W., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.12475 · Cited by 8
Accelerating CNN Training by Pruning Activation GradientsPreprint
Ye, X., Dai, P., Luo, J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.00173 · Cited by 8
Dynamic Origin-Destination Matrix Prediction with Line Graph Neural Networks and Kalman FilterPreprint
Xiong, X., Özbay, K. M. A., Li, J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.00406 · Cited by 8
Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and ActivationsPreprint
Zhuang, B., Liu, J., Tan, M., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.04680 · Cited by 8
GODS: Generalized One-class Discriminative Subspaces for Anomaly DetectionPreprint
Wang, J., & Cherian, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.05884 · Cited by 8
ACNN: a Full Resolution DCNN for Medical Image SegmentationPreprint
Zhou, X.-Y., Zheng, J.-Q., Li, P., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.09203 · Cited by 8
Efficient Learning of Distributed Linear-Quadratic ControllersPreprint
Fattahi, S., Matni, N., & Sojoudi, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.09895 · Cited by 8
Particle reconstruction of volumetric particle image velocimetry with strategy of machine learningPreprint
Gao, Q., Pan, S., Wang, H., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.07815 · Cited by 8
Deep Neural Networks for Choice Analysis: A Statistical Learning Theory PerspectivePreprint
Wang, S., Wang, Q., Bailey, N., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.10465 · Cited by 8
Xiao, D., Liu, C., Wang, Q., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.10783 · Cited by 8
Compressed Video Action Recognition with Refined Motion VectorPreprint
Cao, H., Yu, S., & Feng, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.02533 · Cited by 8
Abdelhalim, I., Mohamed, M. F., & Mahdy, Y. B. (2019) · Expert systems with applications · doi:10.48550/arxiv.1910.11960 · Cited by 151
Detection of pre-microRNA with Convolutional Neural NetworksPreprint
Cordero, J., Menkovski, V., & Allmer, J. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/840579 · Cited by 8
Any-Precision Deep Neural NetworksPreprint
Yu, H., Li, H., Shi, H., Huang, T. S., & Hua, G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.07346 · Cited by 16
Rethinking Normalization and Elimination Singularity in Neural NetworksPreprint
Qiao, S., Wang, H., Liu, C., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.09738 · Cited by 8
Multi-Task Driven Feature Models for Thermal Infrared TrackingPreprint
Liu, Q., Li, X., He, Z., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.11384 · Cited by 8
Adversarial Domain Adaptation with Domain MixupPreprint
Xu, M., Zhang, J., Ni, B., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.01805 · Cited by 8
Machine UnlearningPreprint
Bourtoule, L., Chandrasekaran, V., Choquette-Choo, C. A., Jia, H., Travers, A., Zhang, B., Lie, D., & Papernot, N. (2019) · arXiv (Cornell University) · Cited by 8
Leveraging End-to-End Speech Recognition with Neural Architecture SearchPreprint
Baruwa, A., Abisiga, M., Gbadegesin, I., & Fakunle, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.05946 · Cited by 15
Text as Environment: A Deep Reinforcement Learning Text Readability Assessment ModelPreprint
Mohammadi, H., Khasteh, S. H., Firoozi, T., & Samavati, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.05957 · Cited by 18
Adversarial Cross-Domain Action Recognition with Co-AttentionPreprint
Pan, B., Cao, Z., Adeli, E., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.10405 · Cited by 8
Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps
Dao, T., Sohoni, N. S., Gu, A., Eichhorn, M., Blonder, A., Leszczynski, M., Rudra, A., & Ré, C. (2020) · arXiv · doi:10.48550/arxiv.2012.14966 · Cited by 21
A Deep Neuro-Fuzzy Network for Image ClassificationPreprint
Yazdanbakhsh, O., & Dick, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.01686 · Cited by 39
Revisiting Landscape Analysis in Deep Neural Networks: Eliminating Decreasing Paths to InfinityPreprint
Liang, S., Sun, R., & Srikant, R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.13472 · Cited by 8
An Efficient Hardware Accelerator for Structured Sparse Convolutional Neural Networks on FPGAsPreprint
Zhu, C., Huang, K., Yang, S., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.01955 · Cited by 8
Schindler, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.00251 · Cited by 14
AlignSeg: Feature-Aligned Segmentation NetworksPreprint
Huang, Z., Wei, Y., Wang, X., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.00872 · Cited by 8
When Person Re-identification Meets Changing ClothesPreprint
Wan, F., Wu, Y., Qian, X., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.04070 · Cited by 8
Learn to Augment: Joint Data Augmentation and Network Optimization for Text RecognitionPreprint
Luo, C., Zhu, Y., Jin, L., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.06606 · Cited by 8
Circumventing Outliers of AutoAugment with Knowledge DistillationPreprint
Wei, L., Xiao, A., Xie, L., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.11342 · Cited by 8
Hybrid Models for Open Set RecognitionPreprint
Zhang, H., Li, A., Guo, J. J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.12506 · Cited by 8
MiLeNAS: Efficient Neural Architecture Search via Mixed-Level ReformulationPreprint
He, C., Ye, H., Shen, L., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.12238 · Cited by 8
Hedging with Linear Regressions and Neural NetworksPreprint
Ruf, J., & Wang, W. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3580132 · Cited by 8
Predictive Analysis of COVID-19 Time-series Data from Johns Hopkins UniversityPreprint
Javid, A. M., Liang, X., Venkitaraman, A., & Chatterjee, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.05060 · Cited by 8
Estimating and Exploiting the Impact of Photo Layout in the Sharing EconomyPreprint
Li, H., Simchi‐Levi, D., Wu, M. X., & Zhu, W. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3470877 · Cited by 8
Classifications of Breast Cancer Images by Deep LearningPreprint
Liu, W., hualan, L., Hua, C., & Zhao, L. (2020) · medRxiv · doi:10.1101/2020.06.13.20130633 · Cited by 8
COVID19 detection from Radiographs: Is Deep Learning able to handle the crisis?Preprint
Saqib, M., Anwar, S., Anwar, A., Petersson, L., & Blumenstein, M. (2020) · doi:10.36227/techrxiv.12476426.v1 · Cited by 8
Temporal dynamics of the neural representation of hue and luminance polarityPreprint
Hermann, K. L., Singh, S. R., Rosenthal, I. A., Pantazis, D., & Conway, B. R. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.06.17.155713 · Cited by 9
Efficient Unpaired Image Dehazing with Cyclic Perceptual-Depth SupervisionPreprint
Liu, C., Fan, J., & Yin, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.05220 · Cited by 7
Data from Model: Extracting Data from Non-robust and Robust ModelsPreprint
Benz, P., Zhang, C., Imtiaz, T., & Kweon, I.-S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.06196 · Cited by 8
Rajpal, S., Kumar, N., V, & Rajpal, A. (2020) · arXiv (Cornell University) · Cited by 7
Gesture Recognition for Initiating Human-to-Robot HandoversPreprint
Kwan, J., Tan, C., & Cosgun, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.09945 · Cited by 8
Geodesics, Splines, and Embeddings in Spaces of Images
Rajković, M. (2023) · bonndoc (University of Bonn) · Cited by 8
Maaß, W., Parsons, J., Purao, S., Rosales, A., Storey, V. C., & WOO, C. C. (2017) · Springer eBooks · doi:10.1007/978-3-319-32001-4_505-1 · Cited by 9
Adv-watermark: A Novel Watermark Perturbation for Adversarial ExamplesPreprint
Jia, X., Wei, X., Cao, X., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.01919 · Cited by 8
Xie, Y., Xiong, Y., & Zhu, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.03970 · Cited by 8
Why Machines Matter for Survey and Social Science Researchers
Buskirk, T. D., & Kirchner, A. (2020) · doi:10.1002/9781118976357.ch1 · Cited by 8
Region Comparison Network for Interpretable Few-shot Image ClassificationPreprint
Xue, Z., Duan, L., Li, W., Chen, L., & Luo, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.03558 · Cited by 14
Adaptive Label SmoothingPreprint
Krothapalli, U., & Abbott, A. L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.06432 · Cited by 14
Decision-based Universal Adversarial AttackPreprint
Wu, J., Zhou, M., Liu, S., Liu, Y., & Zhu, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.07024 · Cited by 13
Grasp-type Recognition Leveraging Object AffordancePreprint
Wake, N., Sasabuchi, K., & Ikeuchi, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.09813 · Cited by 8
Real-time Mask Detection on Google Edge TPUPreprint
Park, K., Jang, W., Lee, W., Nam, K., Seong, K., Chai, K., & Li, W.-S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.04427 · Cited by 8
ComboLoss for Facial Attractiveness Analysis with Squeeze-and-Excitation NetworksPreprint
Xu, L., & Xiang, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.10721 · Cited by 8
Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response JacobiansPreprint
Bae, J., & Grosse, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.13514 · Cited by 11
Towards Spatial Variability Aware Deep Neural Networks (SVANN): A Summary of ResultsPreprint
Gupta, J., Xie, Y., & Shekhar, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.08992 · Cited by 14
Beyond Cats and Dogs: Semi-supervised Classification of fuzzy labels with overclusteringPreprint
Schmarje, L., Brünger, J., Santarossa, M., Schröder, S., Kiko, R., & Koch, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.01768 · Cited by 9
Explaining Deep Learning Models for Structured Data using Layer-Wise Relevance PropagationPreprint
Ullah, I., Rios, A., Gala, V., & McKeever, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.13429 · Cited by 8
StressNet: Deep Learning to Predict Stress With Fracture Propagation in Brittle MaterialsPreprint
Wang, Y.-N., Oyen, D., Guo, W., Mehta, A., Scott, C. B., Panda, N., Fernández-Godino, M. G., Srinivasan, G., & Yue, X.-W. (2020) · arXiv.org · doi:10.48550/arxiv.2011.10227 · Cited by 44
Look the Part? The Role of Profile Pictures in Online Labor MarketsPreprint
Troncoso, I., & Luo, L. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3709554 · Cited by 8
CuratorNet: Visually-aware Recommendation of Art ImagesPreprint
Messina, P., Cartagena, M., Cerda-Mardini, P., del Rio, F., & Parra, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.04426 · Cited by 13
Scaling Down Deep Learning with MNIST-1DPreprint
Greydanus, S., & Kobak, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.14439 · Cited by 22
Perceptron Theory for Predicting the Accuracy of Neural Networks.Preprint
Kleyko, D. V., Rosato, A., Frady, E. P., et al. (2020) · arXiv (Cornell University) · Cited by 8
ReMix: Calibrated Resampling for Class Imbalance in Deep learningPreprint
Bellinger, C., Corizzo, R., & Japkowicz, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.02312 · Cited by 17
Metadata
- Authors
- Krizhevsky, A., Sutskever, I., & Hinton, G. E.
- Affiliations
- Google (United States) (US)
- University of Toronto (CA)
- Venue
- Communications of the ACM
- Published
- 2017-05-24
- Volume
- 60
- Issue
- 6
- Pages
- 84-90
- ISSN
- 0001-0782 (ISSN-L)
- 1557-7317
- OpenAlex
- W2163605009
- Cited by
- 112,155
- References
- 27
- Citations by year
- 2026: 2710 · 2025: 7710 · 2024: 10211 · 2023: 12267 · 2022: 12280 · 2021: 15497 · 2020: 14538 · 2019: 13976 · 2018: 9999 · 2017: 6661
- FWCI
- 5127.18
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Communications of the ACM (publishedVersion)
- neural information processing systems
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- ImageNet, image classification, deep convolutional neural networks, dropout regularization, overfitting
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
